INDEX

Explanations

assertions related to testing in a programming context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

test assertions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AnimationsModule

-0.50



-0.46

-0.45

DispatchToProps

-0.43

 currentNode

-0.42

Donor

-0.42

deinit

-0.42

cellaneous

-0.41

 stringBy

-0.41

 nodeId

-0.41

POSITIVE LOGITS

assertEquals

1.84

AreEqual

0.81

Equals

0.77

assertEqual

0.72

toEqual

0.70

XCTAssertEqual

0.70

assertSame

0.63

addGap

0.63

 AssemblyVersion

0.60

assertTrue

0.60

Activations Density 0.002%

assertions related to testing in a programming context

test assertions

No Comments

No Known Activations